Play 73
Waste & Recycling Optimizer
AI-powered waste management — material classification, route optimization, contamination detection.
AI-powered waste management system combining computer vision material classification, collection route optimization, and contamination detection. Azure AI Vision identifies waste types (recyclable/compostable/landfill) from camera feeds, OpenAI generates route optimization considering vehicle capacity and pickup schedules, IoT Hub tracks bin fill levels, and Cosmos DB stores recycling rate analytics for municipality dashboards.
Architecture Pattern
Vision + IoT waste management: material classification → route optimization → contamination alerts
Azure Services
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — Waste Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (186 lines), evaluate (132 lines), tune (230 lines)
- 4 prompts — /deploy, /test, /review, /evaluate with agent routing
- .vscode/mcp.json — FrootAI MCP with Custom Vision + Maps inputs + envFile
TuneKit (AI Config)
- config/openai.json — classification and optimization prompts
- config/waste.json — material categories, vehicle capacity, pickup windows
- config/guardrails.json — classification confidence thresholds
- evaluation/eval.py — Classification accuracy >90%, Route efficiency >85%
Tuning Parameters
Machine evidence
FrootAI evidence lifecycle
This is an internal evidence maturity label, not third-party certification, accreditation, legal compliance, or a production guarantee. Missing or expired evidence demotes automatically; catalog claims cannot promote a play.
This play currently has design evidence only. A runnable scenario, endpoint evaluation, and build receipts are the next contiguous gates.
Repo Intelligence
v1A no-clone, revision-pinned map for agents and humans. Observed evidence is separated from inferred flow so the output stays useful without pretending to be a full call graph.